-
如题，想问一下，albert_large_zh在文本分类的任务上有什么特殊的地方吗？
-
# General
[从Word Embedding到Bert模型——自然语言处理预训练技术发展史](https://www.jiqizhixin.com/articles/2018-12-10-8)
[CS224n自然语言处理与深度学习笔记汇总](https://zhuanlan.zhihu.com/p/31977759)
[深度nlp科普专栏](https://zhuanlan.zhih…
-
test-zhihu-forpredict-v4only-title.txt ，请分享一下，谢谢
-
In program **train.py** of the above repository, I have added two lines at each checkpoint after importing the hiddenlayer as below:
```
hl_graph = hl.build_graph(tf_graph, cnn.input_x)
hl_graph.sa…
-
PaddleNLP\emotion_detection 模型预测封装为服务类，多线程调用，当超过3个线程以上运行时，
pred = exe.run(infer_program,
feed={feed_names[0]: data,
feed_names[1]: seq_lens},
…
-
初步写了个FastText的配置类：https://github.com/maoding1/sinaCrawler/blob/master/eval.py 其他模型的预测可以改改__init__方法里的配置试试
-
**Is your feature request related to a problem? Please describe.**
Running full fledged Elasticsearch cluster to search short strings seems like an overkill.
**Describe the solution you'd like**
…
-
Hi,I want to know why there are 5 input layers in your CNN models,
current_input = Input(shape=(SAMPLE_LENGTH, embedding_size)),currently on the web, I just find the length of input layer is 1.
tha…
-
Goal: better feature/model discoverability for the GluonNLP website
### Side Navigation Bar
* Installation
* Models
* Tutorials
* Demos (in the future)
* API Documentations
* Community…
-
您好，我最近阅读了《Automatic-Software-Vulnerability-Assessment-by-Extracting-Vulnerability-Elements》这篇论文，有所启发。您能分享这篇论文的代码吗，非常感谢。